HIERARCHICAL HMM-BASED SEMANTIC CONCEPT LABELING MODEL

被引：1

作者：

Mengistu, Kinfe Tadesse ^{[1
]}

Hannemann, Mirko ^{[1
]}

Baum, Tobias ^{[1
]}

Wendemuth, Andreas ^{[1
]}

机构：

[1] Otto VonGuericke Univ Magdegurg, FEIT IESK, Cognit Syst Grp, D-39106 Magdeburg, Germany

来源：

2008 IEEE WORKSHOP ON SPOKEN LANGUAGE TECHNOLOGY: SLT 2008, PROCEEDINGS | 2008年

关键词：

Hidden Markov model; Hierarchical model; Semantic concept; Spoken language understanding;

D O I：

10.1109/SLT.2008.4777839

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

An utterance can be conceived as a hidden sequence of semantic concepts expressed in words or phrases. The problem of understanding the meaning underlying a spoken utterance in a dialog system can be partly solved by decodincy the hidden sequence of semantic concepts from the observed sequence of words. In this paper, we describe a hierarchical HMM-based semantic concept labeling model trained on semantically unlabeled data. The hierarchical model is compared with a flat-concept based model in terms of performance, ambiguity resolution ability and expressive power of the output. It is shown that the proposed method outperforms the flat-concept model in these points.

引用

页码：57 / 60

页数：4

共 50 条

[41] EVALUATION OF HMM-BASED LAUGHTER SYNTHESIS
Urbain, Jerome
Cakmak, Huseyin
Dutoit, Thierry
[J]. 2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 7835 - 7839
[42] HMM-based Prosodic Structure Model Using Rich Linguistic Context
Obin, Nicolas
Rodet, Xavier
Lacheret, Anne
[J]. 11TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2010 (INTERSPEECH 2010), VOLS 1-2, 2010, : 1133 - +
[43] HMM-based Speaker Characteristics Emphasis Using Average Voice Model
Nose, Takashi
Adada, Junichi
Kobayashi, Takao
[J]. INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5, 2009, : 2599 - 2602
[44] HMM-Based Vietnamese Speech Synthesis
Trinh, Son
Hoang, Kiem
[J]. INTERNATIONAL JOURNAL OF SOFTWARE INNOVATION, 2015, 3 (04) : 33 - 47
[45] Inverse filter based excitation model for HMM-based speech synthesis system
Reddy, Mittapalle Kiran
Rao, Krothapalli Sreenivasa
[J]. IET SIGNAL PROCESSING, 2018, 12 (04) : 544 - 548
[46] A Discrete HMM-Based Feature Sequence Model Approach for Star Identification
Sun, Li
Jiang, Jie
Zhang, Guangjun
Wei, Xinguo
[J]. IEEE SENSORS JOURNAL, 2016, 16 (04) : 931 - 940
[47] A training method of average voice model for HMM-based speech synthesis
Yamagishi, J
Tamura, M
Masuko, T
Tokuda, K
Kobayashi, T
[J]. IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2003, E86A (08) : 1956 - 1963
[48] HMM-based emotional speech synthesis using average emotion model
Qin, Long
Ling, Zhen-Hua
Wu, Yi-Jian
Zhang, Bu-Fan
Wang, Ren-Hua
[J]. CHINESE SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, 2006, 4274 : 233 - +
[49] Prosodic variation enhancement using unsupervised context labeling for HMM-based expressive speech synthesis
Maeno, Yu
Nose, Takashi
Kobayashi, Takao
Koriyama, Tomoki
Ijima, Yusuke
Nakajima, Hideharu
Mizuno, Hideyuki
Yoshioka, Osamu
[J]. SPEECH COMMUNICATION, 2014, 57 : 144 - 154
[50] HMM-based Speech Synthesis with a Flexible Mandarin Stress Adaptation Model
Li, Ya
Pan, Shifeng
Tao, Jianhua
[J]. 2010 IEEE 10TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS (ICSP2010), VOLS I-III, 2010, : 625 - 628

← 1 2 3 4 5 →